
# df = pd.read_csv('./data.csv',index_col = 0)
df = pd.read_pickle('./data/df_2017-5k.pkl')


# # df = pd.read_csv('./data.csv',index_col = 0)
# df = pd.read_pickle('./df_marathon.pkl')
# df.head(1)


df['finish_time'] = df['time_100'].map(lambda x: x[-1])


## Checking after finish timed added 
## display the dataset
df


## display full dataset with added column finish time
obs = 100#df.shape[0]
pd.set_option('display.max_rows', obs)


athlete_wid = widgets.Dropdown(
    options=df.hashedid.unique(),
    description='Athelte Ids:',
    disabled=False,
)
display(athlete_wid)

Dropdown(description='Athelte Ids:', options=('9a344e1b10a653c2cee3d40cabd615d46d2604198b15bb62069effaee37ba27…


athlete_id = athlete_wid.value
row = df[df.hashedid==athlete_id].copy()
row


group_labels = ['distplot']


fig = ff.create_distplot(row.heartrate_100.tolist(), 
                         group_labels,
                        show_hist=False)\
    .add_traces(px.histogram(row.heartrate_100.item(),pattern_shape_sequence=[ "-"])
    .update_traces(yaxis="y3", name="histogram")
    .data)

fig.update_layout(yaxis3={"overlaying": "y", "side": "right"},
                  bargap=0.2, showlegend=False,
                  xaxis_title="Heart Rate",
                 title = "Heart Rate and KDE for an Individual")
fig.update_xaxes(showgrid=False)
fig.update_yaxes(showgrid=False)
fig.show()


### Pace Vs hearrate
row


def plot_col_hr(row,x_col,y1_col,y2_col,if_col2 = True):
    col,y1col,y2col =  x_col.split("_")[0],y1_col.split("_")[0],y2_col.split("_")[0]
    fig = go.Figure()
    fig.add_trace(go.Scatter(x=row[x_col].item(), y=row[y1_col].item(),
                        mode='lines+markers',
                        name=f'{col} vs {y1col}'))
    title = f"{col} vs {y1col}"
    if if_col2:
        fig.add_trace(go.Scatter(x=row[x_col].item(), y=row[y2_col].item(),
                            mode='lines+markers',
                            name=f'{col} vs {y2col}'))
        title = f"{col} vs {y1col} and {y2col}"

    fig.update_layout( xaxis_title=f"{col}",
                    yaxis_title=f"{y1col}",title = title,
                    dragmode="zoom",
                    hovermode="x",
    legend=dict(traceorder="reversed"),)
    
    fig.show()

x_col = 'distance_100'
y1_col = 'heartrate_100'
y2_col = ''
plot_col_hr(row.copy(),x_col,y1_col,y2_col,False)


x_col = 'pace_diff_100'
y1_col = 'heartrate_100'
y2_col = ''
mean_row_df = row[[x_col,y1_col]].copy()#.groupby(x_col).mean().reset_index()

# plot_col_hr(row.copy(),x_col,y1_col,y2_col,False)
# mean_row_df
cols = [x_col,y1_col]
mean_row_df = row.explode(cols)[cols].copy().groupby(x_col).mean().reset_index()
mean_row_df = mean_row_df.sort_values(by = x_col)


fig = go.Figure()
fig.add_trace(go.Scatter(x=mean_row_df[x_col], y=mean_row_df[y1_col],
                    mode='lines+markers',
                    name=f'Pace Difference vs Heart Rate'))
title = f"Pace Difference vs Heart Rate"

# fig.update_xaxes(showgrid=False)
# fig.update_yaxes(showgrid=False)
fig.update_layout( xaxis_title='Pace Difference',
                yaxis_title="Heart Rate",title = title,
                dragmode="zoom",
                hovermode="x",
legend=dict(traceorder="reversed"))

fig.show()


x_col = 'time_100'
y1_col = 'heartrate_100'
y2_col = ''
plot_col_hr(row,x_col,y1_col,y2_col,False)


x_col = 'time_100'
y1_col = 'pace_diff_100'
y2_col = ''
plot_col_hr(row,x_col,y1_col,y2_col,False)


pdiff = np.array(row['pace_diff_100'].item())
pdiff[pdiff<1] = pdiff.mean()
row['pace_diff_100'] = [pdiff]

row['cardiac_cost_100'] = None

row['cardiac_cost_100'] = [np.array(row.heartrate_100.item())/np.array(row.pace_diff_100.item())/6000.]


x_col = 'distance_100'
y1_col = 'cardiac_cost_100'
y2_col = ''
plot_col_hr(row.copy(),x_col,y1_col,y2_col,False)


x_col = 'heartrate_100'
y1_col = 'cardiac_cost_100'
y2_col = ''
mean_row_df = row[[x_col,y1_col]].copy()#.groupby(x_col).mean().reset_index()

# plot_col_hr(row.copy(),x_col,y1_col,y2_col,False)
# mean_row_df
cols = [x_col,y1_col]
mean_row_df = row.explode(cols)[cols].copy().groupby(x_col).mean().reset_index()
mean_row_df = mean_row_df[(np.abs(stats.zscore(mean_row_df[x_col])) < 1)]
mean_row_df = mean_row_df.sort_values(by = x_col)



fig = go.Figure()
fig.add_trace(go.Scatter(x=mean_row_df[x_col], y=mean_row_df[y1_col],
                    mode='lines+markers',
                    name=f'Cardiac Cost vs Heart Rate'))
title = f"Cardiac Cost vs Heart Rate"

# fig.update_xaxes(showgrid=False)
# fig.update_yaxes(showgrid=False)
fig.update_layout( xaxis_title="Heart Rate",
                yaxis_title="Cardiac Cost",title = title,
                dragmode="zoom",
                hovermode="x",
legend=dict(traceorder="reversed"),)

fig.show()


x_col = 'pace_diff_100'
y1_col = 'cardiac_cost_100'
y2_col = ''
mean_row_df = row[[x_col,y1_col]].copy()#.groupby(x_col).mean().reset_index()

# plot_col_hr(row.copy(),x_col,y1_col,y2_col,False)
# mean_row_df
cols = [x_col,y1_col]
mean_row_df = row.explode(cols)[cols].copy().groupby(x_col).mean().reset_index()
mean_row_df = mean_row_df[(np.abs(stats.zscore(mean_row_df[x_col])) < 2)]
mean_row_df = mean_row_df.sort_values(by = x_col)



fig = go.Figure()
fig.add_trace(go.Scatter(x=mean_row_df[x_col], y=mean_row_df[y1_col],
                    mode='lines+markers',
                    name=f'Pace Difference vs Cardiac Cost'))
title = f"Pace Difference vs Cardiac Cost"

# fig.update_xaxes(showgrid=False)
# fig.update_yaxes(showgrid=False)
fig.update_layout( xaxis_title="Pace Difference",
                yaxis_title="Cardiac Cost",title = title,
                dragmode="zoom",
                hovermode="x",
legend=dict(traceorder="reversed"),)

fig.show()


    
x_col = 'cardiac_cost_100'
y1_col = 'heartrate_100'
y2_col = 'pace_diff_100'

mean_row_df = row[[x_col,y1_col,y2_col]].copy()#.groupby(x_col).mean().reset_index()

# plot_col_hr(row.copy(),x_col,y1_col,y2_col,False)
# mean_row_df
cols = [x_col,y1_col,y2_col]
mean_row_df = row.explode(cols)[cols].copy().groupby(x_col).mean().reset_index()
mean_row_df = mean_row_df[(np.abs(stats.zscore(mean_row_df[x_col])) < 2)]
mean_row_df = mean_row_df.sort_values(by = x_col)



fig = go.Figure()
fig.add_trace(go.Scatter(x=mean_row_df[x_col], y=mean_row_df[y1_col],
                    mode='lines+markers',
                    name=f'cc vs heart rate'))

fig.add_trace(go.Scatter(x=mean_row_df[x_col], y=mean_row_df[y2_col],
                    mode='lines+markers',
                    name=f'cc vs pace diff'))

title = f"Cardiac Cost vs Heart rate and Pace"

# fig.update_xaxes(showgrid=False)
# fig.update_yaxes(showgrid=False)
fig.update_layout( xaxis_title=x_col,
                yaxis_title="pace | heart rate",title = title,
                dragmode="zoom",
                hovermode="x",
legend=dict(traceorder="reversed"),)

fig.show()


x_col = 'distance_100'
y1_col = 'heartrate_100'
y2_col = ""
plot_col_hr(row.copy(),x_col,y1_col,y2_col,if_col2=False)


    
x_col = 'cardiac_cost_100'
y1_col = 'heartrate_100'
y2_col = ''
mean_row_df = row[[x_col,y1_col]].copy()#.groupby(x_col).mean().reset_index()

# plot_col_hr(row.copy(),x_col,y1_col,y2_col,False)
# mean_row_df
cols = [x_col,y1_col]
mean_row_df = row.explode(cols)[cols].copy().groupby(x_col).mean().reset_index()
mean_row_df = mean_row_df[(np.abs(stats.zscore(mean_row_df[x_col])) < 1)]
mean_row_df = mean_row_df.sort_values(by = x_col)



fig = go.Figure()
fig.add_trace(go.Scatter(x=mean_row_df[x_col], y=mean_row_df[y1_col],
                    mode='lines+markers',
                    name=f'Cardiac Cost vs Heart Rate'))
title = f"Cardiac Cost vs Heart Rate"

# fig.update_xaxes(showgrid=False)
# fig.update_yaxes(showgrid=False)
fig.update_layout( xaxis_title="Cardiac Cost",
                yaxis_title="Heart Rate",title = title,
                dragmode="zoom",
                hovermode="x",
legend=dict(traceorder="reversed"),)

fig.show()


#detecting peaks
def detect_peaks(heartrate, threshold=0.3, qrs_filter=None):
    
    if qrs_filter is None:
        # create default qrs filter, which is just a part of the sine function
        t = np.linspace(1.5 * np.pi, 3.5 * np.pi, 15)
        qrs_filter = np.sin(t)
    heartrate = np.array(heartrate)
    
    # normalize data
    heartrate = (heartrate - heartrate.mean()) / heartrate.std()

  
    similarity = np.correlate(heartrate, qrs_filter, mode="same")
    similarity = similarity / np.max(similarity)
    
    heartrate =   heartrate.tolist()
    peaks=[]
    for i in range(len(heartrate)):
        if heartrate[i]>threshold:
            peaks.append(i)
    return peaks, similarity

def plot_hrp(row):
    heartrate_100 = row.heartrate_100
    time_100 = row.time_100
    l=[]
    t=[]
    l=heartrate_100
    t=time_100                     
    peaks, similarity = detect_peaks(l, threshold=0.3)
    # Extract Peak points in heart rate
    # plot 3 way
                    
    a=[]
    c=[]
    for i in range(len(peaks)):
        b=peaks[i]
        a.append(l[b])
    for i in range(len(peaks)):
        b=peaks[i]
        c.append(t[b])
    plt.figure(figsize=(20, 15))
    
    plt.subplot(211)
    plt.title("Heart rates with  peaks")
    plt.plot(c, a, label="Heartrate", color="#51A6D8",marker="o", linewidth=1)
    plt.legend(loc="upper right")
    plt.xlabel("Time ")
    plt.ylabel("Heartrate")  
    plt.subplot(212)
    plt.title('Similarity with QRS ')
    plt.plot(t, similarity, label="Similarity with QRS ", color="olive", linewidth=1)
    plt.legend(loc="upper right")
    plt.xlabel("Time ")
    plt.ylabel("Similarity (normalized)")
    

    
plot_hrp(df.iloc[0])


# df[['heartrate_100','pace_diff_100']].head()
df = df[(df.heartrate_100.str.len()>0)&
   (df.pace_diff_100.str.len()!=0)].copy()
df['cardiac_cost_100'] = df.apply(lambda row: np.array(row.heartrate_100)\
                                  /np.array(row.pace_diff_100)/6000.
                                 ,axis=1)

df['avg_heart_rate'] = df.heartrate_100.map(lambda x : np.array(x).mean())


## Calculating Heart Rate Zones
MIN_HR_POSSIBLE = 30
MAX_HR_POSSIBLE = 200

distance_100 = row.distance_100

# heart_rates = np.array([y for x in df.heartrate_100.values for y in x])
# heart_rates = heart_rates[(heart_rates>MIN_HR_POSSIBLE)&(heart_rates<MAX_HR_POSSIBLE)]
max_hr, min_hr = min(df.avg_heart_rate.max(),MAX_HR_POSSIBLE),max(df.avg_heart_rate.min(),MIN_HR_POSSIBLE)

limits = np.arange(0.5,1.01,0.1)
zone_limits = max_hr*limits  

idxs = np.arange(0,2).reshape(1,-1) + np.arange(0,5).reshape(-1,1)
zone_limits = zone_limits[idxs]
zones_df = pd.DataFrame(zone_limits,columns = ['min_h','max_h'])
zones_df['height'] =zones_df['max_h'] - zones_df['min_h']
zones_df['zone'] = zones_df.index + 1
zones_df['zone'] = 'zone '+ zones_df.zone.astype('str')

zones_df


fig = px.scatter(zones_df, x="min_h", y="max_h",
	         size="height", color="zone"
                 , log_x=True, size_max=60)
fig.show()


import matplotlib.pyplot as plt
import seaborn as sns

def plot_hrz(row):
    distance_100 = row.distance_100
    heartrate_100 = row.heartrate_100
    
    maxh = max(heartrate_100)
    limit1 = maxh*0.50 # 50 percent of Maxh
    limit2 = maxh*0.60 # 60 percent of Maxh
    limit3 = maxh*0.70 # 70 percent of Maxh
    limit4 = maxh*0.80 # 80 percent of Maxh
    limit5 = maxh*0.90 # 90 percent of Maxh
    
    zones = ["Zone 1\n({:.0f}-{:.0f})".format(limit1, limit2),
             "Zone 2\n({:.0f}-{:.0f})".format(limit2, limit3),
             "Zone 3\n({:.0f}-{:.0f})".format(limit3, limit4),
             "Zone 4\n({:.0f}-{:.0f})".format(limit4, limit5),
             "Zone 5\n({:.0f}-{:.0f})".format(limit5, maxh)]
    
    values = [sum(1 for hr in heartrate_100 if hr >= limit1 and hr < limit2),
              sum(1 for hr in heartrate_100 if hr >= limit2 and hr < limit3),
              sum(1 for hr in heartrate_100 if hr >= limit3 and hr < limit4),
              sum(1 for hr in heartrate_100 if hr >= limit4 and hr < limit5),
              sum(1 for hr in heartrate_100 if hr >= limit5)]
    
    plt.bar(zones, values)
    plt.title("Heart Rate Zones for Athlete")
    plt.xlabel("Heart Rate Zones")
    plt.ylabel("Number of performer spend")
    plt.show()

plot_hrz(df.iloc[0])


## Zone wise heart rate for performer
### Zone Wise Heart Rate , Cardiac cost and Pace

def get_zone(hrate):
    _zone_df = zones_df[(zones_df.max_h >= hrate) & (zones_df.min_h <= hrate)]
    if not _zone_df.empty:
        return _zone_df['zone'].iloc[-1]
    return None
def plot_groups(group,df_group):

    # create subplots with 1 row and 3 columns
    zones = zones_df.zone.unique()
    for zone in zones:
        fig = make_subplots(rows=1, cols=4)

        df_zone_group = df_group[df_group['zone']==zone]
        if df_zone_group.empty or df_zone_group.shape[0]<2: #atleast 2 datapoints
            continue
        # loop over the three columns in df
        for i, col in enumerate(['avg_cardiac_cost', 'avg_heart_rate', 'avg_time','avg_pace_diff']):
            # add a boxplot for the current column to the subplot
            fig.add_trace(px.box(df_zone_group[col], points="all", boxmode="overlay").data[0], row=1, col=i+1)
            fig.update_xaxes(showgrid=False, row=1, col=i+1)
            fig.update_yaxes(showgrid=False, row=1, col=i+1)

        fig.update_layout(title = f"{zone} : Plotting Heart Rate, Pace Diff, Time and Cardiac cost for {group} Group")
        fig.show()

df['zone'] = df.avg_heart_rate.map(lambda x:get_zone(x))
df['avg_cardiac_cost'] = df.cardiac_cost_100.map(lambda x : np.array(x).mean()) 
df['avg_pace_diff'] = df.pace_diff_100.map(lambda x : np.array(x).mean())


df['avg_time'] = df.time_100.apply(lambda x: np.array(x).mean())
 
def plot_zones(group,df_group):

    # create subplots with 1 row and 3 columns
    fig = make_subplots(rows=1, cols=3)
    # loop over the three columns in df
    for i, col in enumerate(['avg_cardiac_cost', 'avg_heart_rate','avg_pace_diff']):
        # add a boxplot for the current column to the subplot
        fig.add_trace(px.box(df_zone_group[col], points="all", boxmode="overlay").data[0], row=1, col=i+1)
        fig.update_xaxes(showgrid=False, row=1, col=i+1)
        fig.update_yaxes(showgrid=False, row=1, col=i+1)

        fig.update_layout(title = f"{zone} : Plotting Heart Rate, Pace Diff and Cardiac cost")
        fig.show()
zone = 'zone 1'
df_group = df[df.zone==zone].copy()
plot_groups(zone,df_group)


zone = 'zone 2'
df_group = df[df.zone==zone].copy()
plot_groups(zone,df_group)


def plot_groups(group,df_group):

    # create subplots with 1 row and 3 columns
    zones = zones_df.zone.unique()
    for zone in zones:
        fig = make_subplots(rows=1, cols=4)

        df_zone_group = df_group[df_group['zone']==zone]
        if df_zone_group.empty or df_zone_group.shape[0]<2: #atleast 2 datapoints
            continue
        # loop over the three columns in df
        for i, col in enumerate(['avg_cardiac_cost', 'avg_heart_rate', 'avg_time','avg_pace_diff']):
            # add a boxplot for the current column to the subplot
            fig.add_trace(px.box(df_zone_group[col], points="all", boxmode="overlay").data[0], row=1, col=i+1)
            fig.update_xaxes(showgrid=False, row=1, col=i+1)
            fig.update_yaxes(showgrid=False, row=1, col=i+1)

        fig.update_layout(title = f"{zone} : Plotting Heart Rate, Pace Diff, Time and Cardiac cost for {group} Group")
        fig.show()


zone = 'zone 3'
df_group = df[df.zone==zone].copy()
plot_groups(zone,df_group)


zone = 'zone 4'
df_group = df[df.zone==zone].copy()
plot_groups(zone,df_group)


zone = 'zone 5'
df_group = df[df.zone==zone].copy()
plot_groups(zone,df_group)


df['finish_time_hrs'] = df['finish_time']/3600
SLOW,MED,FAST = 'slow','medium','fast'

# df['finish_time_hrs'] = pd.to_datetime(df['finish_time'], unit='m').dt.time

def div_perform(finish_time):
    if finish_time < 3.5:
        return FAST
    elif 3.5 < finish_time <4.5:
        return MED
    else:
        return SLOW
    


df['group'] = df.finish_time_hrs.map(lambda x : div_perform(x))


# get the value counts of the 'group' column
value_counts = df['group'].value_counts(dropna=False)

# create a pie chart using plotly express
fig = px.pie(names=value_counts.index, values=value_counts.values, hole=0.5)

# set the title and hover text
fig.update_layout(
    title="Counts of Each Group",
    hovermode="closest",
    annotations=[dict(text=f"Athlete Groups", 
                      x=0.5, y=0.5, font_size=20, showarrow=False)
                 for count in value_counts.values],
)
fig.update_traces(textinfo='value')

# show the plot
fig.show()


group = 'slow'
df_group = df[df.group==group].copy()
plot_groups(group,df_group)


df_slow = df[df.group=='slow']
df_slow = df_slow[df_slow.avg_heart_rate<181.813229] # remove this check later
df_slow.loc[df_slow.zone.isnull(),'zone'] = 'zone 1'
df_slow = df_slow.sort_values(by='zone')

fig = px.box(df_slow, x="zone", y="avg_cardiac_cost",points="all")
fig.update_layout(title = f"Cardiac Cost for different Zones for Slow Group")

fig.show()


df_slow = df[df.group=='slow']
df_slow = df_slow[df_slow.avg_heart_rate<181.813229] # remove this check later
df_slow.loc[df_slow.zone.isnull(),'zone'] = 'zone 1'
df_slow = df_slow.sort_values(by='zone')

fig = px.box(df_slow, x="zone", y="avg_heart_rate",points="all")
fig.update_layout(title = f"Heart Rate for different Zones for Slow Group")

fig.show()


df_slow = df[df.group=='slow']
df_slow = df_slow[df_slow.avg_heart_rate<181.813229] # remove this check later
df_slow.loc[df_slow.zone.isnull(),'zone'] = 'zone 1'
df_slow = df_slow.sort_values(by='zone')

fig = px.box(df_slow, x="zone", y="avg_pace_diff",points="all")
fig.update_layout(title = f"Pace Difference for different Zones for Slow Group")

fig.show()


df_slow = df[df.group=='slow']
df_slow = df_slow[df_slow.avg_heart_rate<181.813229] # remove this check later
df_slow.loc[df_slow.zone.isnull(),'zone'] = 'zone 1'
df_slow = df_slow.sort_values(by='zone')

fig = px.box(df_slow, x="zone", y="avg_time",points="all")
fig.update_layout(title = f"Time for different Zones for Slow Group")

fig.show()


fig = px.scatter(df_slow, x="zone", y="avg_cardiac_cost", color="zone",
                 size='finish_time_hrs', hover_data=['avg_cardiac_cost'])
fig.show()


fig = px.scatter(df_slow, x="zone", y="avg_time", color="zone",
                 size='finish_time_hrs', hover_data=['avg_cardiac_cost'])
fig.show()


fig = px.scatter(df_slow, x="zone", y="avg_pace_diff", color="zone",
                 size='finish_time_hrs', hover_data=['avg_cardiac_cost'])
fig.show()


fig = px.scatter(df_slow, x="zone", y="avg_heart_rate", color="zone",
                 size='finish_time_hrs', hover_data=['avg_cardiac_cost'])
fig.show()


fig = px.scatter(df_slow, x="finish_time_hrs", y="avg_cardiac_cost", color="zone",
                 size='finish_time_hrs', hover_data=['avg_cardiac_cost'])
fig.show()


fig = px.scatter(df_slow, x="finish_time_hrs", y="avg_time", color="zone",
                 size='finish_time_hrs', hover_data=['avg_time'])
fig.show()


fig = px.scatter(df_slow, x="finish_time_hrs", y="avg_heart_rate", color="zone",
                 size='finish_time_hrs', hover_data=['avg_heart_rate'])
fig.show()


fig = px.scatter(df_slow, x="finish_time_hrs", y="avg_pace_diff", color="zone",
                 size='finish_time_hrs', hover_data=['avg_pace_diff'])
fig.show()


group = 'medium'
df_group = df[df.group==group].copy()
plot_groups(group,df_group)


### Plotting Pace Difference for all zones in Medium group

df_med = df[df.group=='medium']
df_med = df_med.sort_values(by='zone')

fig = px.box(df_med, x="zone", y="avg_pace_diff",points="all")
fig.update_layout(title = f"Pace Difference for different Zones for Medium Group")

fig.show()


df_med = df[df.group=='medium']
df_med = df_med.sort_values(by='zone')

fig = px.box(df_med, x="zone", y="avg_time",points="all")
fig.update_layout(title = f"Time for different Zones for Medium Group")

fig.show()


df_med = df[df.group=='medium']
df_med = df_med.sort_values(by='zone')

fig = px.box(df_med, x="zone", y="avg_heart_rate",points="all")
fig.update_layout(title = f"Heart Rate for different Zones for Medium Group")

fig.show()


df_med = df[df.group=='medium']
df_med = df_med.sort_values(by='zone')

fig = px.box(df_med, x="zone", y="avg_cardiac_cost",points="all")
fig.update_layout(title = f"Cardiac Cost for different Zones for Medium Group")

fig.show()


cols = ['avg_cardiac_cost','avg_heart_rate','avg_pace_diff','avg_time']

for col in cols:
    fig = px.scatter(df_med, x="zone", y=col, color="zone",
                     size='finish_time_hrs', hover_data=[col])
    fig.update_layout(title = f"{col} for different Zones for Medium Group")

    fig.show()


cols = ['avg_cardiac_cost','avg_heart_rate','avg_pace_diff','avg_time']

for col in cols:
    fig = px.scatter(df_med, x="finish_time_hrs", y=col, color="zone",
                     size='finish_time_hrs', hover_data=[col])
    fig.update_layout(title = f"{col} vs Finish Time(hrs) for different Zones in Medium Group")

    fig.show()


df_fast = df[df.group=='fast']
df_fast = df_fast.sort_values(by='zone')

fig = px.box(df_fast, x="zone", y="avg_time",points="all")
fig.update_layout(title = f"Time for different Zones for fast Group")

fig.show()


df_fast = df[df.group=='fast']
df_fast = df_fast.sort_values(by='zone')

fig = px.box(df_fast, x="zone", y="avg_cardiac_cost",points="all")
fig.update_layout(title = f"Cardiac Cost for different Zones for fast Group")

fig.show()


df_fast = df[df.group=='fast']
df_fast = df_fast.sort_values(by='zone')

fig = px.box(df_fast, x="zone", y="avg_heart_rate",points="all")
fig.update_layout(title = f"Heart Rate for different Zones for fast Group")

fig.show()


df_fast = df[df.group=='fast']
df_fast = df_fast.sort_values(by='zone')

fig = px.box(df_fast, x="zone", y="avg_pace_diff",points="all")
fig.update_layout(title = f"Pace Difference for different Zones for fast Group")

fig.show()


cols = ['avg_cardiac_cost','avg_heart_rate','avg_pace_diff','avg_time']

for col in cols:
    fig = px.scatter(df_fast, x="zone", y=col, color="zone",
                     size='finish_time_hrs', hover_data=[col])
    fig.update_layout(title = f"{col} for different Zones for Fast Group")

    fig.show()


cols = ['avg_cardiac_cost','avg_heart_rate','avg_pace_diff','avg_time']

for col in cols:
    fig = px.scatter(df_fast, x="finish_time_hrs", y=col, color="zone",
                     size='finish_time_hrs', hover_data=[col])
    fig.update_layout(title = f"{col} vs Finish Time(hrs) for different Zones in Fast Group")

    fig.show()


group = 'fast'
df_group = df[df.group==group].copy()
plot_groups(group,df_group)


df_grouped = df[['group','zone','avg_cardiac_cost',
                 'avg_pace_diff','avg_heart_rate']].groupby(['group','zone']).mean().copy()

df_grouped


fig = go.Figure()

for group in df_grouped.index.get_level_values('group').unique():
    group_data = df_grouped.loc[group]
    fig.add_trace(go.Scatter3d(
        x=group_data['avg_cardiac_cost'],
        y=group_data['avg_pace_diff'],
        z=group_data['avg_heart_rate'],
        mode='markers',
        name=group,
        text=group_data.index.get_level_values('zone'),
        marker=dict(
            size=10,
            opacity=0.8
        )
    ))

fig.update_layout(scene=dict(
                    xaxis_title='Avg Cardiac Cost',
                    yaxis_title='Avg Pace Diff',
                    zaxis_title='Avg Heart Rate'))

fig.show()


def plot_zone_cols(group):
    df_ = df[df.group==group].copy()
    for col in ['avg_heart_rate','avg_cardiac_cost','avg_time','avg_pace_diff']:
        avg_col_df_raw = df_[['zone',col]].groupby(['zone']).mean()
        avg_col_df_raw = avg_col_df_raw.reset_index()
        num_performers = df_.hashedathleteid.nunique()
        avg_col_df = df_[['zone',col]].groupby(['zone']).sum()/num_performers
        avg_col_df = avg_col_df.rename(columns={col:f'{col} - (combined)'})
        avg_col_df = avg_col_df.reset_index().merge(avg_col_df_raw)
        avg_col_df = pd.concat([avg_col_df,
                                pd.DataFrame([['zone 1',1e-7,1e-7]],columns=['zone',f'{col} - (combined)',col])])
        avg_col_df = avg_col_df.sort_values(by='zone').reset_index(drop=True)
        display(avg_col_df)
        # Create a histogram with heart rate columns side by side
        fig = px.histogram(avg_col_df, x="zone", y=[f'{col} - (combined)', col],
                           barmode="group", 
                           labels={"value": col},
                           title=f"Distribution of {col} by Zone",
                           color_discrete_sequence=["#636EFA", "#EF553B"])

        # Adjust the bar gaps
        fig.update_layout(bargap=0.1, bargroupgap=0.2)

        # Show the plot
        fig.show()
        
group = 'slow'
plot_zone_cols(group)


group = 'medium'
plot_zone_cols(group)


group = 'fast'
plot_zone_cols(group)


def plot_relation(df):
    fig = px.scatter(df, x='avg_pace_diff', y='avg_heart_rate', trendline='ols')
    fig.update_layout()
    
    fig.update_layout(
        title='Relation between Pace Diff and Heart Rate'
    )

    fig.show()

    cols = ['avg_heart_rate','avg_pace_diff']
    corr = df[cols].corr()

    fig = go.Figure(data=go.Heatmap(
                       z=corr.values,
                       x=corr.columns,
                       y=corr.index,
                       colorscale='RdBu',
                       zmin=-1,
                       zmax=1,
                       colorbar=dict(title='Correlation'),
                       text=corr.round(2),
                       hovertemplate='Correlation: %{text:.2f}<extra></extra>'
                     ))

    annotations = []
    for i, row in enumerate(corr.index):
        for j, col in enumerate(corr.columns):
            annotation = dict(
                x=col,
                y=row,
                text=f'{corr.iloc[i, j]:.2f}',
                font=dict(color='black'),
                showarrow=False
            )
            annotations.append(annotation)

    fig.update_layout(
        title='Correlation Heatmap b/w Pace Diff and Heart Rate',
        annotations=annotations
    )

    fig.show()
    
df_slow = df[df.group=='slow'].copy()
plot_relation(df_slow)


df_med = df[df.group=='medium'].copy()
plot_relation(df_med)


df_fast = df[df.group=='fast'].copy()
plot_relation(df_fast)


def hr_group_pred(df):
    col = 'heartrate_100'
    df[col] = df[col].apply(lambda x: x[:len(x)//2])
    df_col = pd.DataFrame(df[col].tolist())
    # there are a couple of noise values in df so just filling them with mean

    df_col = df_col.fillna(df_col.mean())

    print("Extracted heart rate column and created a new dataframe by exploding the previous df")
    display(df_col.head(2))
    
    num_cols = df_col.shape[1]

    print("dividing data into test train split")
    X_train, X_test, y_train, y_test = train_test_split(df_col, df['finish_time_hrs'], test_size=0.4,shuffle = False)
    xgb = XGBRegressor()
    
    xgb.fit(X_train, y_train)
    y_pred = xgb.predict(X_test).flatten()
    mse = np.mean((y_pred - y_test)**2)
    print(f"Mean Squared Error: {mse}")
    # create a scatter plot with your data and predictions

    # add a line plot for your xgboost predictions
#     fig.add_trace(go.Scatter(x=df['x'], y=df['preds'], mode='lines', name='XGBoost Predictions'))

    
    df_ = pd.DataFrame()
    df_['avg_heart_rate'] = df.iloc[y_test.index[0]:]['avg_heart_rate']
    df_['y_test'] = y_test
    df_['y_pred'] = y_pred
    df_ = df_.sort_values(by='avg_heart_rate')

    #create scatterplot with regression line
    sns.regplot(data = df_, x='avg_heart_rate', y = 'y_pred')
    
    # returing test set and predictions
    return y_test,y_pred,mse


def cc_group_pred(df):
    col = 'cardiac_cost_100'
    df[col] = df[col].apply(lambda x: x[:len(x)//2])
    df_col = pd.DataFrame(df[col].tolist())
    # there are a couple of noise values in df so just filling them with mean

    df_col = df_col.fillna(df_col.mean())

    print("Extracted Cardiac Cost column and created a new dataframe by exploding the previous df")
    display(df_col.head(2))
    
    num_cols = df_col.shape[1]

    print("dividing data into test train split")
    X_train, X_test, y_train, y_test = train_test_split(df_col, df['finish_time_hrs'], test_size=0.3,shuffle = False)
    xgb = XGBRegressor()

    xgb.fit(X_train, y_train)
    y_pred = xgb.predict(X_test).flatten()
    mse = np.mean((y_pred - y_test)**2)
    print(f"Mean Squared Error: {mse}")
    
    
    df_ = pd.DataFrame()
    df_['avg_cardiac_cost'] = df.iloc[y_test.index[0]:]['avg_cardiac_cost']
    df_['y_test'] = y_test
    df_['y_pred'] = y_pred
    df_ = df_.sort_values(by='avg_cardiac_cost')

    #create scatterplot with regression line
    sns.regplot(data = df_, x='avg_cardiac_cost', y = 'y_pred')
    
    # returing test set and predictions
    return y_test,y_pred,mse


df_results = pd.DataFrame([],columns = ["group","hr_error",'cc_error'])


df_slow = df_slow.reset_index(drop=True)
y_test,y_pred,cc_mse = cc_group_pred(df_slow)
df_slow_cc_results = df_slow.iloc[y_test.index[0]:].copy().reset_index(drop=True)
df_slow_cc_results['predicted_finish_time'] = y_pred

Extracted Cardiac Cost column and created a new dataframe by exploding the previous df

dividing data into test train split
Mean Squared Error: 0.18433761434206034


df_slow = df_slow.reset_index(drop=True)
y_test,y_pred,hr_mse = hr_group_pred(df_slow)
df_slow_hr_results = df_slow.iloc[y_test.index[0]:].copy().reset_index(drop=True)
df_slow_hr_results['predicted_finish_time'] = y_pred
df_slow_hr_results = df_slow_hr_results.sort_values(by='finish_time_hrs')


new_df = pd.DataFrame([["slow",hr_mse,cc_mse]],columns= ["group","hr_error",'cc_error'])
df_results = pd.concat([df_results, new_df], axis=0, ignore_index=True)

Extracted heart rate column and created a new dataframe by exploding the previous df

dividing data into test train split
Mean Squared Error: 0.27460432596066603


# df_slow_hr_results[['finish_time_hrs','predicted_finish_time']]
def comparison_hr_cc(df_hr_results,df_cc_results):
    df_hr_results = df_hr_results.rename(columns={'predicted_finish_time':'hr_predicted_finish_time'})
    df_cc_results = df_cc_results.rename(columns={'predicted_finish_time':'cc_predicted_finish_time'})
    hr_cols = ['hashedid','finish_time_hrs','hr_predicted_finish_time']
    cc_cols = ['hashedid','cc_predicted_finish_time']
    df_res = df_cc_results[cc_cols].merge(df_hr_results[hr_cols],how='inner')

    df_res_columns = ['cc_predicted_finish_time','hr_predicted_finish_time']
    fig = go.Figure()

    # plotting the predictions
    for i, algo in enumerate(df_res_columns):
        fig.add_trace(
            go.Scatter(
                x=df_res['finish_time_hrs'],
                y=df_res[algo],
                mode='markers',
                name=algo
            )
        )

    fig.update_layout(
        title='Comparison of Finish Time predictions using Cardiac Cost, Pace and Heart Rate',
        xaxis_title='True Finish Time values',
        yaxis_title='Predicted Finish Time values'
    )

    fig.show()
comparison_hr_cc(df_slow_hr_results,df_slow_cc_results)


df_med = df_med.reset_index(drop=True)
y_test,y_pred,cc_mse = cc_group_pred(df_med)
df_med_cc_results = df_med.iloc[y_test.index[0]:].copy().reset_index()
df_med_cc_results['predicted_finish_time'] = y_pred

Extracted Cardiac Cost column and created a new dataframe by exploding the previous df

dividing data into test train split
Mean Squared Error: 0.05121551416699187


y_test,y_pred,hr_mse = hr_group_pred(df_med)
df_med_hr_results = df_med.iloc[y_test.index[0]:].copy().reset_index()
df_med_hr_results['predicted_finish_time'] = y_pred
df_med_hr_results = df_med_hr_results.sort_values(by='finish_time_hrs')
# fig = px.line(df_med_hr_results, x="finish_time_hrs", y="predicted_finish_time", title='finish Time MSE')
# fig.show()


new_df = pd.DataFrame([["medium",hr_mse,cc_mse]],columns= ["group","hr_error",'cc_error'])
df_results = pd.concat([df_results, new_df], axis=0, ignore_index=True)

Extracted heart rate column and created a new dataframe by exploding the previous df

dividing data into test train split
Mean Squared Error: 0.07764102109278646


comparison_hr_cc(df_med_hr_results,df_med_cc_results)
# df_med_cc_results


df_fast = df_fast.reset_index(drop=True)
y_test,y_pred,cc_mse = cc_group_pred(df_fast)
df_fast_cc_results = df_fast.iloc[y_test.index[0]:].copy().reset_index()
df_fast_cc_results['predicted_finish_time'] = y_pred

Extracted Cardiac Cost column and created a new dataframe by exploding the previous df

dividing data into test train split
Mean Squared Error: 0.055999146859345976


y_test,y_pred,hr_mse = hr_group_pred(df_fast)
df_fast_hr_results = df_fast.iloc[y_test.index[0]:].copy().reset_index()
df_fast_hr_results['predicted_finish_time'] = y_pred
df_fast_hr_results = df_fast_hr_results.sort_values(by='finish_time_hrs')
# fig = px.line(df_med_hr_results, x="finish_time_hrs", y="predicted_finish_time", title='finish Time MSE')
# fig.show()


new_df = pd.DataFrame([["fast",hr_mse,cc_mse]],columns= ["group","hr_error",'cc_error'])
df_results = pd.concat([df_results, new_df], axis=0, ignore_index=True)

Extracted heart rate column and created a new dataframe by exploding the previous df

dividing data into test train split
Mean Squared Error: 0.07423839817618307


df_results


comparison_hr_cc(df_fast_hr_results,df_fast_cc_results)
# df_med_cc_results


fig = px.histogram(df_results, x='group', y=['hr_error', 'cc_error'],
                   barmode='group', title='Histogram of Errors by Group')

fig.update_yaxes(title='MSE error')
fig.show()

	hashedid	hashedathleteid	startdate	startdatelocal	totaldistance	elevgain	startlatapprox	startlngapprox	cumulative_elevation_gain	cumulative_elevation_loss	...	geog	distance_100	time_100	elevation_100	cadence_100	heartrate_100	pace_diff_100	pace_cumul_100	gap_100	finish_time
0	9a344e1b10a653c2cee3d40cabd615d46d2604198b15bb...	197b3e2a67167805191c315e64640e5b3aa0dae4a7cba3...	2017-10-29 09:10:29	2017-10-29 09:10:29	42311.3	271.600	53.33	-6.25	235.0	187.0	...	0101000020E610000000000000000019C0000000803DAA...	[0.0, 100.0, 200.0, 300.0, 400.0, 500.0, 600.0...	[0.0, 38.98845, 75.44795, 112.36312, 143.05545...	[18.3, 17.900051, 17.956602, 17.997967, 17.303...	[]	[124.0, 138.00153, 158.49796, 172.15256, 183.9...	[1e-05, 6.682236, 6.02834, 5.416158, 4.943549,...	[25.0, 6.498075, 6.287327, 6.242397, 5.960643,...	[0.0, 6.828764, 6.009906, 5.404039, 5.133536, ...	13093.2630
1	9eab2135ab8c8182d2e6eb36c87606efa3418d31a7b152...	85ab08865f60f548c2a362aeadf7d2fac801b0b75d0c21...	2017-10-29 09:10:39	2017-10-29 09:10:39	42461.3	269.913	53.33	-6.25	221.0	202.0	...	0101000020E610000000000000000019C0000000803DAA...	[0.0, 100.0, 200.0, 300.0, 400.0, 500.0, 600.0...	[0.0, 38.141705, 75.420105, 112.58787, 140.797...	[18.0, 18.1182, 18.568665, 18.237965, 17.30003...	[1e-05, 60.776775, 78.99788, 78.99595, 79.3095...	[69.0, 118.00433, 115.79638, 117.72328, 118.03...	[1e-05, 6.744568, 5.696991, 4.160349, 4.65892,...	[25.0, 6.357691, 6.28458, 6.255208, 5.866589, ...	[0.0, 6.701542, 5.559884, 4.235624, 4.902388, ...	14995.8400
2	9ec542cb1a44509fd87521c5743d400987df1433b48544...	ef33b1f6295728ab85be787754de13ef0f22d85546dc95...	2017-10-29 09:02:03	2017-10-29 09:02:03	42396.6	263.140	53.33	-6.25	219.0	203.0	...	0101000020E610000000000000000019C0000000803DAA...	[0.0, 100.0, 200.0, 300.0, 400.0, 500.0, 600.0...	[0.0, 34.051785, 63.714027, 99.33842, 126.0090...	[17.8, 17.979973, 18.573772, 18.525688, 18.340...	[84.0, 86.831635, 87.57081, 85.98568, 88.64971...	[]	[1e-05, 5.229298, 5.400293, 5.635104, 4.725854...	[25.0, 5.686955, 5.31107, 5.518765, 5.250323, ...	[0.0, 5.178599, 5.229725, 5.649802, 4.773427, ...	13152.5990
3	9ec8e3139fcd0b60af668440d0560c30d4eec6faf9ede5...	ffa2c7a60a904ff047b58e43bb4a1c17e55fbbcf173127...	2017-10-29 08:55:33	2017-10-29 08:55:33	42621.4	282.699	53.34	-6.25	213.0	212.0	...	0101000020E610000000000000000019C00000002085AB...	[0.0, 100.0, 200.0, 300.0, 400.0, 500.0, 600.0...	[0.0, 363.61026, 395.8846, 423.8148, 459.01483...	[17.1, 18.10048, 18.188477, 18.501003, 18.2008...	[]	[]	[1e-05, 4.854006, 5.094511, 4.652123, 4.432908...	[25.0, 25.0, 25.0, 23.5453, 19.125616, 16.3804...	[0.0, 4.598914, 5.070293, 4.574117, 4.505633, ...	12864.3190
4	9f0e9a093a823fcf03a22948c4e417c4de0a4bf126b865...	3168b39d03feaa62356a49abbadf57ccec493d7a25de23...	2017-10-29 09:00:25	2017-10-29 09:00:25	42489.4	195.000	53.33	-6.25	217.0	206.0	...	0101000020E610000000000000000019C0000000803DAA...	[0.0, 100.0, 200.0, 300.0, 400.0, 500.0, 600.0...	[0.0, 33.269478, 64.696045, 98.46664, 124.9062...	[-132.2, -131.97264, -131.61813, -131.48433, -...	[60.0, 92.47492, 94.040146, 94.219345, 96.0676...	[108.0, 129.89734, 134.17978, 135.58492, 141.1...	[1e-05, 5.756402, 4.844161, 4.206395, 4.504928...	[25.0, 5.546336, 5.391422, 5.470671, 5.204367,...	[0.0, 5.685999, 4.752145, 4.17603, 4.401713, 4...	11219.2430
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
3161	9bf625b142d3122895b9883cead4af52d44e2173dfc7b5...	92e8d744e080ee1f1f1c37894af12fdbc264b4335dc4eb...	2017-10-29 09:01:53	2017-10-29 09:01:53	42501.1	265.380	53.33	-6.25	209.0	214.0	...	0101000020E610000000000000000019C0000000803DAA...	[0.0, 100.0, 200.0, 300.0, 400.0, 500.0, 600.0...	[0.0, 30.884827, 61.23929, 93.71124, 123.22373...	[17.1, 18.095196, 18.597677, 18.302849, 18.451...	[1e-05, 79.952736, 85.98579, 84.81591, 87.0576...	[]	[1e-05, 5.281608, 4.70696, 5.168903, 4.654006,...	[25.0, 5.143316, 5.10306, 5.206595, 5.134331, ...	[0.0, 5.005465, 4.5808, 5.252191, 4.616716, 4....	12758.8955
3162	9c22d775800b2d1e4614329c62d3354960acf10466d603...	59e8991532737aded81123b9162b968f44237d4c58aebb...	2017-10-29 08:34:00	2017-10-29 08:34:00	22082.4	107.000	53.34	-6.26	110.0	122.0	...	0101000020E6100000000000803D0A19C00000002085AB...	[0.0, 100.0, 200.0, 300.0, 400.0, 500.0, 600.0...	[0.0, 24.843252, 57.57859, 85.12957, 105.17841...	[99.2, 99.011215, 98.36667, 98.54853, 99.62743...	[59.0, 86.02894, 86.65374, 88.05222, 86.984566...	[]	[1e-05, 3.631549, 4.744741, 4.87496, 0.556868,...	[25.0, 4.142016, 4.796249, 4.729414, 4.382618,...	[0.0, 3.668899, 4.913648, 4.827204, 0.525386, ...	12429.2870
3163	9c33c97ef0b99bd4f42cca563b8b73d16d1caf82569892...	c6325a263405cbe4861c5354921329594861aca902faa2...	2017-10-29 08:11:24	2017-10-29 08:11:24	42655.7	211.800	53.33	-6.25	192.0	189.0	...	0101000020E610000000000000000019C0000000803DAA...	[0.0, 100.0, 200.0, 300.0, 400.0, 500.0, 600.0...	[0.0, 38.05753, 76.406944, 119.077934, 154.057...	[56.8, 55.800014, 56.8, 56.8, 56.8, 56.8, 56.7...	[1e-05, 84.0, 83.10598, 83.0, 83.0, 82.99874, ...	[116.0, 128.04362, 129.0, 128.03062, 133.00156...	[1e-05, 5.612709, 6.130106, 6.102883, 5.490096...	[25.0, 6.342913, 6.367242, 6.615442, 6.419069,...	[0.0, 5.926004, 5.808106, 6.102883, 5.490096, ...	15421.2430
3164	9c4f3f7c353748094548e6670cdc7028ca484d733f31b7...	c6fae963e810e1a1c11c771e2a77d6c88a6a5d41a3eb27...	2017-10-29 09:31:39	2017-10-29 09:31:39	44568.3	288.207	53.34	-6.25	240.0	205.0	...	0101000020E610000000000000000019C00000002085AB...	[0.0, 100.0, 200.0, 300.0, 400.0, 500.0, 600.0...	[0.0, 50.392284, 97.46559, 146.05293, 194.7328...	[17.7, 18.191647, 18.70834, 18.121914, 18.6573...	[]	[]	[1e-05, 7.141158, 9.09016, 19.81336, 8.482373,...	[25.0, 8.399151, 8.121722, 8.113903, 8.113851,...	[0.0, 6.95382, 8.839737, 20.45398, 8.240371, 2...	24714.9730
3165	9c6d3c0560d73025be19d0f945e0a76714c11e0de580a8...	bf27b30646e3a79875c16c0d172bcdb272ce3cd4168a00...	2017-10-29 09:01:40	2017-10-29 09:01:40	42488.3	186.000	53.33	-6.25	218.0	206.0	...	0101000020E610000000000000000019C0000000803DAA...	[0.0, 100.0, 200.0, 300.0, 400.0, 500.0, 600.0...	[0.0, 29.10826, 60.614273, 102.052956, 131.584...	[5.6, 5.875436, 6.228689, 6.326708, 5.797177, ...	[1e-05, 89.92593, 90.01278, 85.70384, 87.6375,...	[107.0, 136.8759, 143.56119, 140.79216, 141.82...	[1e-05, 4.97735, 5.525431, 5.20914, 4.94926, 6...	[25.0, 4.852088, 5.051579, 5.669946, 5.482744,...	[0.0, 4.903712, 5.420839, 5.181566, 5.093511, ...	12931.0580

	min_h	max_h	height	zone
0	100.0	120.0	20.0	zone 1
1	120.0	140.0	20.0	zone 2
2	140.0	160.0	20.0	zone 3
3	160.0	180.0	20.0	zone 4
4	180.0	200.0	20.0	zone 5

		avg_cardiac_cost	avg_pace_diff	avg_heart_rate
group	zone
fast	zone 1	3.666077	4.177152	114.064704
	zone 2	6.422354	4.344681	133.020681
	zone 3	6.060830	4.639915	153.138853
	zone 4	8.383007	4.590122	168.096919
	zone 5	7.225559	4.406520	183.827969
medium	zone 1	12.267995	7.153221	114.907737
	zone 2	8.663070	5.785085	133.908162
	zone 3	8.005074	5.634214	153.276322
	zone 4	7.240500	5.599993	167.687618
	zone 5	5.696055	5.558052	183.376041
slow	zone 1	8.667584	7.709010	113.950045
	zone 2	8.799938	7.162069	133.510517
	zone 3	8.280546	7.149391	151.948541
	zone 4	9.003134	6.858199	167.265080
	zone 5	9.772631	7.252094	183.041151

	zone	avg_heart_rate - (combined)	avg_heart_rate
0	zone 1	1.068282e+00	1.139500e+02
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	1.460271e+01	1.335105e+02
3	zone 3	6.172909e+01	1.519485e+02
4	zone 4	7.422388e+01	1.672651e+02
5	zone 5	2.288014e+00	1.830412e+02

	zone	avg_cardiac_cost - (combined)	avg_cardiac_cost
0	zone 1	8.125860e-02	8.667584e+00
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	9.624933e-01	8.799938e+00
3	zone 3	3.363972e+00	8.280546e+00
4	zone 4	3.995141e+00	9.003134e+00
5	zone 5	1.221579e-01	9.772631e+00

	zone	avg_time - (combined)	avg_time
0	zone 1	8.851202e+01	9.441282e+03
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	9.758279e+02	8.921855e+03
3	zone 3	3.553194e+03	8.746323e+03
4	zone 4	3.744831e+03	8.439057e+03
5	zone 5	1.119820e+02	8.958560e+03

	zone	avg_pace_diff - (combined)	avg_pace_diff
0	zone 1	7.227197e-02	7.709010e+00
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	7.833513e-01	7.162069e+00
3	zone 3	2.904440e+00	7.149391e+00
4	zone 4	3.043326e+00	6.858199e+00
5	zone 5	9.065117e-02	7.252094e+00

	zone	avg_heart_rate - (combined)	avg_heart_rate
0	zone 1	5.229021e-01	1.149077e+02
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	3.656196e+00	1.339082e+02
3	zone 3	6.207778e+01	1.532763e+02
4	zone 4	8.928078e+01	1.676876e+02
5	zone 5	4.798235e+00	1.833760e+02

	zone	avg_cardiac_cost - (combined)	avg_cardiac_cost
0	zone 1	5.582705e-02	1.226799e+01
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	2.365343e-01	8.663070e+00
3	zone 3	3.242100e+00	8.005074e+00
4	zone 4	3.855010e+00	7.240500e+00
5	zone 5	1.490435e-01	5.696055e+00

	zone	avg_time - (combined)	avg_time
0	zone 1	3.244101e+01	7.128913e+03
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	1.909475e+02	6.993454e+03
3	zone 3	2.804767e+03	6.925254e+03
4	zone 4	3.690299e+03	6.931139e+03
5	zone 5	1.808072e+02	6.909979e+03

	zone	avg_pace_diff - (combined)	avg_pace_diff
0	zone 1	3.255163e-02	7.153221e+00
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	1.579545e-01	5.785085e+00
3	zone 3	2.281889e+00	5.634214e+00
4	zone 4	2.981566e+00	5.599993e+00
5	zone 5	1.454325e-01	5.558052e+00

	zone	avg_heart_rate - (combined)	avg_heart_rate
0	zone 1	7.129044e-01	1.140647e+02
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	4.988276e+00	1.330207e+02
3	zone 3	5.710803e+01	1.531389e+02
4	zone 4	9.385411e+01	1.680969e+02
5	zone 5	3.829749e+00	1.838280e+02

	zone	avg_cardiac_cost - (combined)	avg_cardiac_cost
0	zone 1	2.291298e-02	3.666077e+00
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	2.408383e-01	6.422354e+00
3	zone 3	2.260184e+00	6.060830e+00
4	zone 4	4.680512e+00	8.383007e+00
5	zone 5	1.505325e-01	7.225559e+00

	zone	avg_time - (combined)	avg_time
0	zone 1	3.254211e+01	5.206738e+03
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	1.845386e+02	4.921030e+03
3	zone 3	2.088584e+03	5.600671e+03
4	zone 4	3.090927e+03	5.535988e+03
5	zone 5	1.021278e+02	4.902133e+03

	zone	avg_pace_diff - (combined)	avg_pace_diff
0	zone 1	2.610720e-02	4.177152e+00
1	zone 1	1.000000e-07	1.000000e-07
2	zone 2	1.629255e-01	4.344681e+00
3	zone 3	1.730302e+00	4.639915e+00
4	zone 4	2.562818e+00	4.590122e+00
5	zone 5	9.180250e-02	4.406520e+00

	0	1	2	3	4	5	6	7	8	9	...	280	281	282	283	284	285	286	287	288	289
0	1866.666667	0.003253	0.002552	0.002704	0.003322	0.003421	0.003855	0.003787	0.002956	0.003177	...	0.003781	0.003363	0.00335	0.003219	0.003505	0.003216	0.003409	0.003712	0.003037	0.003333
1	2400.000000	0.002694	0.003253	0.003216	0.003395	0.003579	0.003261	0.003747	0.002955	0.003751	...	0.003781	0.003363	0.00335	0.003219	0.003505	0.003216	0.003409	0.003712	0.003037	0.003333

	0	1	2	3	4	5	6	7	8	9	...	280	281	282	283	284	285	286	287	288	289
0	112.0	149.3608	132.41661	143.04920	140.47089	140.53351	147.19073	145.00604	141.14948	138.20952	...	126.98686	126.0	124.99988	125.0	125.0	125.0	125.0	125.0	125.025215	124.0
1	144.0	143.9577	142.98877	145.28488	143.91667	145.91734	133.09620	147.96850	147.93945	149.23276	...	126.98686	126.0	124.99988	125.0	125.0	125.0	125.0	125.0	125.025215	124.0

	0	1	2	3	4	5	6	7	8	9	...	206	207	208	209	210	211	212	213	214	215
0	2066.666667	0.003442	0.004382	0.005297	0.006202	0.005587	0.006239	0.005129	0.004978	0.007614	...	0.005442	0.005516	0.005342	0.005300	0.005236	8.160218	0.005133	0.004766	0.005501	0.00487
1	1150.000000	0.002916	0.003388	0.004716	0.004223	0.003924	0.003875	0.004336	0.003435	0.004050	...	0.004432	0.004754	0.004756	0.004668	0.004693	0.004732	0.005133	0.004766	0.005501	0.00487

	0	1	2	3	4	5	6	7	8	9	...	206	207	208	209	210	211	212	213	214	215
0	124.0	138.00153	158.49796	172.15256	183.96542	176.97311	183.916340	182.61981	177.90056	180.461300	...	167.99971	166.8640	170.06549	165.99829	164.90790	165.38415	166.331248	165.839582	167.466664	162.196475
1	69.0	118.00433	115.79638	117.72328	118.03809	117.01072	118.757034	124.00983	122.18063	123.031784	...	153.74084	149.6435	153.02608	151.64230	154.37788	155.02983	166.331248	165.839582	167.466664	162.196475

	0	1	2	3	4	5	6	7	8	9	...	209	210	211	212	213	214	215	216	217	218
0	1800.000000	0.003761	0.004617	0.005372	0.005222	0.005516	0.004923	0.00521	0.005423	0.005762	...	0.006561	0.006538	0.006529	0.006223	0.008609	0.005853	0.00625	0.005877	0.006591	0.005901
1	1183.333333	0.005611	0.006052	0.007811	0.006651	0.005979	0.006467	0.00705	0.006349	0.005976	...	0.006428	0.006442	0.006320	0.006223	0.008609	0.005853	0.00625	0.005877	0.006591	0.005901

	0	1	2	3	4	5	6	7	8	9	...	209	210	211	212	213	214	215	216	217	218
0	108.0	129.89734	134.17978	135.58492	141.13550	142.01509	146.00969	143.95483	145.96210	147.24023	...	164.35478	165.96284	167.00540	164.874502	170.30544	156.95015	160.00215	156.04495	157.41348	155.5053
1	71.0	118.21266	133.98340	141.48727	138.82515	141.01483	140.07600	141.81734	144.17122	142.58566	...	155.17902	153.91727	154.00504	164.874502	170.30544	156.95015	160.00215	156.04495	157.41348	155.5053

	group	hr_error	cc_error
0	slow	0.274604	0.184338
1	medium	0.077641	0.051216
2	fast	0.074238	0.055999

Gitlab doesn't render plotly and html. So I am using nbviewer to display the notebooks. Please access it through this link to view rendered notebook¶

Table of Contents¶

Exploratory Data Analysis¶

Calculating finish time¶

Select individual from below¶

Distribution of heart rate for one individual¶

Distance Vs Heart rate¶

Pace Diff vs Heart Rate¶

Time vs Heart rate and Pace Difference for an Individual¶

Plotting Time against Heart Rate¶

Plotting Time against Pace Difference¶

Distance vs Heart rate and Cardiac Cost¶

Distance vs Cardiac Cost¶

Cardiac Cost vs Heart Rate¶

Cardiac Cost vs Heart rate and Pace¶

Distance vs heart Rate Variablity for an individual¶

Cardiac cost¶

detecting peak for the heart rate¶

Calculating Cardiac Cost for All individuals¶

Calculating Heart Rate Zones¶

Plotting the Zones¶

Time spend by the Athlete in each zone¶

Start from here to finish form the new file lets¶

Zone wise heart rate for performer¶

Zone Wise Heart Rate , Cardiac cost and Pace¶

Zone Wise Heart Rate , Cardiac cost and Pace¶

Zone 1 : Heart Rate, Cardiac Cost and Time, Pace Difference¶

Zone 2 : Heart Rate, Cardiac Cost and Pace Difference¶

Zone 3 : Heart Rate, Cardiac Cost and Pace Difference¶

Zone 4 : Heart Rate, Cardiac Cost and Pace Difference¶

Zone 5 : Heart Rate, Cardiac Cost and Pace Difference¶

Dividing Athletes into Groups - Slow, Medium, Fast¶

Percentages of Different groups¶

Slow Group - Heart Rate, Pace Diff and Cardiac Cost¶

Slow Group - Heart Rate, Pace Diff and Cardiac Cost¶

Based on all performers: Plotting Distribution for Different Zones in Group¶

Plotting Cardiac cost for all zones in slow group¶

Plotting Heart Rate for all zones in slow group¶

Plotting Pace Difference for all zones in slow group¶

Plotting average time for all zones in slow group¶

Plotting Cardiac Cost for each zone in slow group¶

Plotting Time for each zone in slow group¶

Plotting Pace Difference for each zone in slow group¶

Plotting Heart Rate for each zone in slow group¶

Plotting Finish Time vs Cardiac Cost for slow group¶

Plotting Finish Time vs Time spent for slow group¶

Plotting Finish Time vs Heart Rate for slow group¶

Plotting Finish Time vs Pace Difference for slow group¶

Medium Group - Heart Rate, Pace Diff and Cardiac Cost¶

Plotting Pace Difference for all zones in Medium group¶

Plotting Time for all zones in Medium group¶

Plotting Heart Rate for all zones in Medium group¶

Plotting Cardiac Cost for all zones in Medium group¶

Fast Group - Heart Rate, Pace Diff and Cardiac Cost¶

Fast Group - Heart Rate, Pace Diff and Cardiac Cost¶

Plotting Cardiac cost, time, pace diff and heart rate for Fast group for different zones¶

Avg. HR, Cardiac Cost, Pace Diff for individuals in each Group + Zone¶

Slow group Zone wise Cardiac Cost, Heart Rate, Pace Diff and Time Spent¶

Medium group Zone wise Cardiac Cost, Heart Rate, Pace Diff and Time Spent¶

Fast group Zone wise Cardiac Cost, Heart Rate, Pace Diff and Time Spent¶

Pace Difference vs Heart Rate relationship for Slow group¶

Pace Difference vs Heart Rate relationship for medium group (weak Inverse relationship)¶

Pace Difference vs Heart Rate relationship for Fast group (weak Inverse relationship)¶

Model¶

Hyperparameters¶

Plotting Distribution of Heart Rate, Pace Difference, Time spent and Cardiac cost for slow group¶

Predicting Finish Time (hrs) based on half values of Cardiact cost, Pace and Heart Rate.¶

Using heart Rate to predict Finish time¶

Using Cardiac Cost to predict Finish time¶

Prediction Results¶

Cardiac Cost¶

Heart Rate¶

Predicting Finish Time for Slow Group¶

Regression Line for Finish time prediction based on Cardiac Cost (Slow Group)¶

Regression Line for Finish time prediction based on Heart Rate (Slow Group)¶

Comparison of Predicted finish time vs actual finish time using Cardiac cost and Heart Rate for Slow group¶

Regression Line for Finish time prediction based on Cardiac Cost (MediumGroup)¶

Regression Line for Finish time prediction based on Heart Rate (Medium Group)¶

Comparison of Predicted finish time vs actual finish time using Cardiac cost and Heart Rate for Medium Group¶

Regression Line for Finish time prediction based on Cardiac Cost (Fast Group)¶